SEMSDNet: A Multiscale Dense Network With Attention for Remote Sensing Scene Classification
Open Access
- 22 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 5501-5514
Abstract
Remote sensing image scene classification plays an important role in remote sensing image interpretation. Deep learning brings prosperity to the research in this field, and numerous deep learning models are proposed in order to improve the performance of scene classification. However, images of different remote sensing scenes vary a lot, showing similar or diverse textures and simple or complex contents. Using a fixed convolution neural network framework to classify scene images is performance-limited and not practice-flexible. To address this issue, in this paper, we propose the SEMSDNet (multi-scale dense networks with squeeze and excitation attention). The framework MSDNet with multiple classifiers and dense connections can automatically transform between a small network and a deep network according to the complexity of test samples and the limitation of computational resources. Moreover, in order to extract more effective features, the squeeze and excitation attention mechanism is introduced into the framework to process the features of various scenes self-adaptively. In addition, considering the limited computing resources, we impose two settings with computational constraints at the test time: budgeted batch classification which is a fixed computational budget setting for sample classification, and anytime prediction which forces the network to output a prediction at any given point-in-time. Experimental results on several public datasets show that the proposed SEMSDNet method is superior to state-of-the-art methods on both performance and efficiency. Experiments also reveal its capability to treat samples of different classification difficulties with uneven resource allocation and flexible network architecture, showing its potentials in practical applications.Keywords
Funding Information
- National Natural Science Foundation of China (42071339, U1711266, 41925007, U1803117, 42071430)
This publication has 43 references indexed in Scilit:
- Scene classification using local and global features with collaborative representation fusionInformation Sciences, 2016
- Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised LearningIEEE Transactions on Geoscience and Remote Sensing, 2016
- Scene Classification via a Gradient Boosting Random Convolutional Network FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2015
- A comparative study of sampling analysis in scene classification of high-resolution remote sensing imagery2015
- Going deeper with convolutions2015
- Saliency-Guided Unsupervised Feature Learning for Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Remote Sensing Image Retrieval With Global Morphological Texture DescriptorsIEEE Transactions on Geoscience and Remote Sensing, 2013
- Double Constrained NMF for Hyperspectral UnmixingIEEE Transactions on Geoscience and Remote Sensing, 2013
- Object-oriented classification of high-resolution remote sensing imagery based on an improved colour structure code and a support vector machineInternational Journal of Remote Sensing, 2010
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998